alihamedi's picture
First Push
dbf8523 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9104623198509216,
"min": 0.9104623198509216,
"max": 2.872694969177246,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8703.109375,
"min": 8703.109375,
"max": 29387.669921875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.64648723602295,
"min": 0.3206540644168854,
"max": 12.64648723602295,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2466.06494140625,
"min": 62.206886291503906,
"max": 2556.84765625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0643919797307093,
"min": 0.062373028103006524,
"max": 0.07448998718995,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2575679189228372,
"min": 0.2499390499890033,
"max": 0.3659507214256069,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21271045374519687,
"min": 0.10060305269343742,
"max": 0.3051617483005804,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8508418149807875,
"min": 0.40241221077374967,
"max": 1.3435222965245153,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.227272727272727,
"min": 3.1818181818181817,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 140.0,
"max": 1364.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.1818181818181817,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 140.0,
"max": 1364.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709968591",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709969072"
},
"total": 480.227553392,
"count": 1,
"self": 0.4360211850000155,
"children": {
"run_training.setup": {
"total": 0.05852089999996224,
"count": 1,
"self": 0.05852089999996224
},
"TrainerController.start_learning": {
"total": 479.733011307,
"count": 1,
"self": 0.5906206179988089,
"children": {
"TrainerController._reset_env": {
"total": 2.6346271729999557,
"count": 1,
"self": 2.6346271729999557
},
"TrainerController.advance": {
"total": 476.4151353710012,
"count": 18200,
"self": 0.2812869839947325,
"children": {
"env_step": {
"total": 476.1338483870065,
"count": 18200,
"self": 315.22535696001137,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.6140301800001,
"count": 18200,
"self": 1.539447865011084,
"children": {
"TorchPolicy.evaluate": {
"total": 159.07458231498902,
"count": 18200,
"self": 159.07458231498902
}
}
},
"workers": {
"total": 0.29446124699501297,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 478.2586643410057,
"count": 18200,
"is_parallel": true,
"self": 236.50062534100311,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004925975999981347,
"count": 1,
"is_parallel": true,
"self": 0.0032859230000212847,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016400529999600622,
"count": 10,
"is_parallel": true,
"self": 0.0016400529999600622
}
}
},
"UnityEnvironment.step": {
"total": 0.0372722010000075,
"count": 1,
"is_parallel": true,
"self": 0.0006604179999385451,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003688270000452576,
"count": 1,
"is_parallel": true,
"self": 0.0003688270000452576
},
"communicator.exchange": {
"total": 0.034182079999993675,
"count": 1,
"is_parallel": true,
"self": 0.034182079999993675
},
"steps_from_proto": {
"total": 0.002060876000030021,
"count": 1,
"is_parallel": true,
"self": 0.00039848800008712715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016623879999428937,
"count": 10,
"is_parallel": true,
"self": 0.0016623879999428937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.7580390000026,
"count": 18199,
"is_parallel": true,
"self": 10.590026164026824,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.592576030984674,
"count": 18199,
"is_parallel": true,
"self": 5.592576030984674
},
"communicator.exchange": {
"total": 189.6136104229932,
"count": 18199,
"is_parallel": true,
"self": 189.6136104229932
},
"steps_from_proto": {
"total": 35.96182638199792,
"count": 18199,
"is_parallel": true,
"self": 6.856044954988931,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.105781427008992,
"count": 181990,
"is_parallel": true,
"self": 29.105781427008992
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013870600002974243,
"count": 1,
"self": 0.00013870600002974243,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 470.6876031670324,
"count": 680027,
"is_parallel": true,
"self": 15.159870137968085,
"children": {
"process_trajectory": {
"total": 261.02708189906417,
"count": 680027,
"is_parallel": true,
"self": 260.52018564606425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5068962529999226,
"count": 4,
"is_parallel": true,
"self": 0.5068962529999226
}
}
},
"_update_policy": {
"total": 194.50065113000016,
"count": 90,
"is_parallel": true,
"self": 60.30737970599699,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.19327142400317,
"count": 4587,
"is_parallel": true,
"self": 134.19327142400317
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09248943900001905,
"count": 1,
"self": 0.0009150399999953152,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09157439900002373,
"count": 1,
"self": 0.09157439900002373
}
}
}
}
}
}
}